RESUMO
BACKGROUND: The distal transradial access (dTRA) has become an attractive and alternative access to the conventional transradial access (TRA) for cardiovascular interventional diagnosis and/or treatment. There was a lack of randomized clinical trials to evaluate the effect of the dTRA on the long-term radial artery occlusion (RAO). METHODS: This was a prospective, randomized controlled study. The primary endpoint was the incidence of long-term RAO at 3 months after discharge. The secondary endpoints included the successful puncture rate, puncture time, and other access-related complications. RESULTS: The incidence of long-term RAO was 0.8% (3/361) for dTRA and 3.3% (12/365) for TRA (risk ratio = 0.25, 95% confidence interval = 0.07-0.88, P = 0.02). The incidence of RAO at 24 h was significantly lower in the dTRA group than in the TRA group (2.5% vs. 6.7%, P < 0.01). The puncture success rate (96.0% vs. 98.5%, P = 0.03) and single puncture attempt (70.9% vs. 83.9%, P < 0.01) were significantly lower in the dTRA group than in the TRA group. However, the number of puncture attempts and puncture time were higher in the dTRA group. The dTRA group had a lower incidence of bleeding than the TRA group (1.5% vs. 6.0%, P < 0.01). There was no difference in the success rate of the procedure, total fluoroscopy time, or incidence of other access-related complications between the two groups. In the per-protocol analysis, the incidence of mEASY type ≥ II haematoma was significantly lower in the dTRA group, which was consistent with that in the as-treated analysis. CONCLUSIONS: The dTRA significantly reduced the incidence of long-term RAO, bleeding or haematoma. TRIAL REGISTRATION: ClinicalTrials.gov identifer: NCT05253820.
Assuntos
Arteriopatias Oclusivas , Intervenção Coronária Percutânea , Humanos , Artéria Radial/cirurgia , Estudos Prospectivos , Arteriopatias Oclusivas/diagnóstico por imagem , Arteriopatias Oclusivas/epidemiologia , Hemorragia , Hematoma/etiologia , Hematoma/complicações , Angiografia Coronária/efeitos adversos , Angiografia Coronária/métodos , Intervenção Coronária Percutânea/efeitos adversos , Intervenção Coronária Percutânea/métodos , Resultado do TratamentoRESUMO
Utilizing light and plastic wastes as resources to turn the wasted phenols and hazardous aryl halides into value added chemicals seems to be an attractive idea for alleviating the energy crisis and environmental problems. In this work, plasmonic copper nanoparticles (Cu NPs) were loaded onto carbon nanotubes (CNTs) from various sources including commercial CNTs and those derived from plastic wastes. Under visible-light irradiation, the catalyst could efficiently convert phenols and aryl halides to diaryl ethers. Similar with commercial CNTs, excellent activity is also achieved when utilizing CNTs derived from different kinds of plastic wastes as support for the system. Further investigation shows that the visible-light irradiation and light-excited plasmonic Cu NPs are necessary to inhibit the phenol degradation on CNTs and in turn promote the cross-coupling of phenol and aryl halides. Compared with metal oxides and other carbon materials, the excellent capability of CNTs to absorb light, to convert light to heat, and to adsorb both two reactants simultaneously are critical to enhance the activity of Cu NPs, achieving high yields of diaryl ethers. This study could provide a novel strategy for catalyst design and generate a more economically sustainable process.
RESUMO
The study aimed to investigate the efficacy and safety of coronary intervention via distal transradial access (dTRA) in patients with low body mass index (BMI). A total of 67 patients with low BMI who underwent coronary intervention, comprising 29 patients via dTRA and 38 patients via conventional transradial access (cTRA), were retrospectively included. There was no significant difference in the puncture success rate between the two groups (dTRA 96.6%, cTRA 97.4%, P=0.846). Compared with the cTRA group, the success rate of one-needle puncture in the dTRA group was lower (51.7% vs. 81.6%, P=0.020). The compression haemostasis time in the dTRA group was shorter than that in the cTRA group (P < 0.001). However, the incidence of radial artery occlusion was lower in the dTRA group than in the cTRA group (4.0% vs. 33.3%, P=0.007). In conclusion, coronary intervention via dTRA was safe and effective in patients with low BMI.
Assuntos
Índice de Massa Corporal , Intervenção Coronária Percutânea , Arteriopatias Oclusivas/epidemiologia , Humanos , Intervenção Coronária Percutânea/efeitos adversos , Intervenção Coronária Percutânea/métodos , Punções , Artéria Radial , Estudos RetrospectivosRESUMO
Electrocatalysis plays a vital role in energy conversion and storage in modern society. Localized surface plasmon resonance (LSPR) is a highly attractive approach to enhance the electrocatalytic activity and selectivity with solar energy. LSPR excitation can induce the transfer of hot electrons and holes, electromagnetic field enhancement, lattice heating, resonant energy transfer and scattering, in turn boosting a variety of electrocatalytic reactions. Although the LSPR-mediated electrocatalysis has been investigated, the underlying mechanism has not been well explained. Moreover, the efficiency is strongly dependent on the structure and composition of plasmonic metals. In this review, the currently proposed mechanisms for plasmon-mediated electrocatalysis are introduced and the preparation methods to design supported plasmonic nanostructures and related electrodes are summarized. In addition, we focus on the characterization strategies used for verifying and differentiating LSPR mechanisms involved at the electrochemical interface. Following that are highlights of representative examples of direct plasmonic metal-driven and indirect plasmon-enhanced electrocatalytic reactions. Finally, this review concludes with a discussion on the remaining challenges and future opportunities for coupling LSPR with electrocatalysis.
RESUMO
The fast pandemics of coronavirus disease (COVID-19) has led to a devastating influence on global public health. In order to treat the disease, medical imaging emerges as a useful tool for diagnosis. However, the computed tomography (CT) diagnosis of COVID-19 requires experts' extensive clinical experience. Therefore, it is essential to achieve rapid and accurate segmentation and detection of COVID-19. This paper proposes a simple yet efficient and general-purpose network, called Sequential Region Generation Network (SRGNet), to jointly detect and segment the lesion areas of COVID-19. SRGNet can make full use of the supervised segmentation information and then outputs multi-scale segmentation predictions. Through this, high-quality lesion-areas suggestions can be generated on the predicted segmentation maps, reducing the diagnosis cost. Simultaneously, the detection results conversely refine the segmentation map by a post-processing procedure, which significantly improves the segmentation accuracy. The superiorities of our SRGNet over the state-of-the-art methods are validated through extensive experiments on the built COVID-19 database.
RESUMO
Pre-training and fine-tuning have been the de-facto paradigm in vision-language domains. Along with the rapid growth of model sizes, fully fine-tuning these large-scale vision-language pre-training (VLP) models requires prohibitively expensive storage costs. To address this issue, recent advances in NLP offer a promising and efficient adaptation approach called LoRA, which aims to approximate the fine-tuning of large pre-trained model by updating low-rank parameters. Despite its effectiveness, we identify that LoRA suffers a large approximation error on VLP models and its optimization is also inefficient, which greatly limits its performance upper bound. In this paper, we mathematically prove that the approximation error of low-rank adaptation can be optimized by a new optimization objective, i.e., the weight distance between LoRA and fine-tuning. Based on this finding, we propose a novel PETL method for VLP models, namely momentum imitation learning (MoIL). Specifically, MoIL formulates PETL as a weight imitation learning process and directly optimize the approximation error bound of the low-rank adaptation. Based on this training scheme, we also explore a new hybrid approximation function to reduce the learning difficulty of low-rank adaptations. With these two novel designs, MoIL can greatly improve the optimization efficiency of the low-rank parameters on VLP models. We validate MoIL on three VLP models ranging from end-to-end network to two-stage network, and conduct extensive experiments on four VL tasks. Experimental results demonstrate superior performance and optimization efficiency of MoIL than existing PETL methods. For instance, by updating only 6.23% parameters, MoIL can even outperform full tuning by +2.3% on image-text matching task. Meanwhile, its inference efficiency and generalization ability is also validated by multiple VLP models, e.g., VLMO and VinVL.
RESUMO
Weakly supervised object localization (WSOL) stands as a pivotal endeavor within the realm of computer vision, entailing the location of objects utilizing merely image-level labels. Contemporary approaches in WSOL have leveraged FPMs, yielding commendable outcomes. However, these existing FPM-based techniques are predominantly confined to rudimentary strategies of either augmenting the foreground or diminishing the background presence. We argue for the exploration and exploitation of the intricate interplay between the object's foreground and its background to achieve efficient object localization. In this manuscript, we introduce an innovative framework, termed adaptive zone learning (AZL), which operates on a coarse-to-fine basis to refine FPMs through a triad of adaptive zone mechanisms. First, an adversarial learning mechanism (ALM) is employed, orchestrating an interplay between the foreground and background regions. This mechanism accentuates coarse-grained object regions in a mutually adversarial manner. Subsequently, an oriented learning mechanism (OLM) is unveiled, which harnesses local insights from both foreground and background in a fine-grained manner. This mechanism is instrumental in delineating object regions with greater granularity, thereby generating better FPMs. Furthermore, we propose a reinforced learning mechanism (RLM) as the compensatory mechanism for adversarial design, by which the undesirable foreground maps are refined again. Extensive experiments on CUB-200-2011 and ILSVRC datasets demonstrate that AZL achieves significant and consistent performance improvements over other state-of-the-art WSOL methods.
RESUMO
Visible-infrared person re-identification (VI-ReID) is the task of matching the same individuals across the visible and infrared modalities. Its main challenge lies in the modality gap caused by the cameras operating on different spectra. Existing VI-ReID methods mainly focus on learning general features across modalities, often at the expense of feature discriminability. To address this issue, we present a novel cycle-construction-based network for neutral yet discriminative feature learning, termed CycleTrans. Specifically, CycleTrans uses a lightweight knowledge capturing module (KCM) to capture rich semantics from the modality-relevant feature maps according to pseudo anchors. Afterward, a discrepancy modeling module (DMM) is deployed to transform these features into neutral ones according to the modality-irrelevant prototypes. To ensure feature discriminability, another two KCMs are further deployed for feature cycle constructions. With cycle construction, our method can learn effective neutral features for visible and infrared images while preserving their salient semantics. Extensive experiments on SYSU-MM01 and RegDB datasets validate the merits of CycleTrans against a flurry of state-of-the-art (SOTA) methods, +1.88% on rank-1 in SYSU-MM01 and +1.1% on rank-1 in RegDB. Our code is available at https://github.com/DoubtedSteam/CycleTrans.
RESUMO
This article explores a novel dynamic network for vision and language (V&L) tasks, where the inferring structure is customized on the fly for different inputs. Most previous state-of-the-art (SOTA) approaches are static and handcrafted networks, which not only heavily rely on expert knowledge but also ignore the semantic diversity of input samples, therefore resulting in suboptimal performance. To address these issues, we propose a novel Dynamic Transformer Network (DTNet) for image captioning, which dynamically assigns customized paths to different samples, leading to discriminative yet accurate captions. Specifically, to build a rich routing space and improve routing efficiency, we introduce five types of basic cells and group them into two separate routing spaces according to their operating domains, i.e., spatial and channel. Then, we design a Spatial-Channel Joint Router (SCJR), which endows the model with the capability of path customization based on both spatial and channel information of the input sample. To validate the effectiveness of our proposed DTNet, we conduct extensive experiments on the MS-COCO dataset and achieve new SOTA performance on both the Karpathy split and the online test server. The source code is publicly available at https://github.com/xmu-xiaoma666/DTNet.
RESUMO
PSNR-oriented models are a critical class of super-resolution models with applications across various fields. However, these models tend to generate over-smoothed images, a problem that has been analyzed previously from the perspectives of models or loss functions, but without taking into account the impact of data properties. In this paper, we present a novel phenomenon that we term the center-oriented optimization (COO) problem, where a model's output converges towards the center point of similar high-resolution images, rather than towards the ground truth. We demonstrate that the strength of this problem is related to the uncertainty of data, which we quantify using entropy. We prove that as the entropy of high-resolution images increases, their center point will move further away from the clean image distribution, and the model will generate over-smoothed images. Implicitly optimizing the COO problem, perceptual-driven approaches such as perceptual loss, model structure optimization, or GAN-based methods can be viewed. We propose an explicit solution to the COO problem, called Detail Enhanced Contrastive Loss (DECLoss). DECLoss utilizes the clustering property of contrastive learning to directly reduce the variance of the potential high-resolution distribution and thereby decrease the entropy. We evaluate DECLoss on multiple super-resolution benchmarks and demonstrate that it improves the perceptual quality of PSNR-oriented models. Moreover, when applied to GAN-based methods, such as RaGAN, DECLoss helps to achieve state-of-the-art performance, such as 0.093 LPIPS with 24.51 PSNR on 4× downsampled Urban100, validating the effectiveness and generalization of our approach.
RESUMO
Transformers have shown remarkable performance, however, their architecture design is a time-consuming process that demands expertise and trial-and-error. Thus, it is worthwhile to investigate efficient methods for automatically searching high-performance Transformers via Transformer Architecture Search (TAS). In order to improve the search efficiency, training-free proxy based methods have been widely adopted in Neural Architecture Search (NAS). Whereas, these proxies have been found to be inadequate in generalizing well to Transformer search spaces, as confirmed by several studies and our own experiments. This paper presents an effective scheme for TAS called TRansformer Architecture search with ZerO-cost pRoxy guided evolution (T-Razor) that achieves exceptional efficiency. Firstly, through theoretical analysis, we discover that the synaptic diversity of multi-head self-attention (MSA) and the saliency of multi-layer perceptron (MLP) are correlated with the performance of corresponding Transformers. The properties of synaptic diversity and synaptic saliency motivate us to introduce the ranks of synaptic diversity and saliency that denoted as DSS++ for evaluating and ranking Transformers. DSS++ incorporates correlation information among sampled Transformers to provide unified scores for both synaptic diversity and synaptic saliency. We then propose a block-wise evolution search guided by DSS++ to find optimal Transformers. DSS++ determines the positions for mutation and crossover, enhancing the exploration ability. Experimental results demonstrate that our T-Razor performs competitively against the state-of-the-art manually or automatically designed Transformer architectures across four popular Transformer search spaces. Significantly, T-Razor improves the searching efficiency across different Transformer search spaces, e.g., reducing required GPU days from more than 24 to less than 0.4 and outperforming existing zero-cost approaches. We also apply T-Razor to the BERT search space and find that the searched Transformers achieve competitive GLUE results on several Neural Language Processing (NLP) datasets. This work provides insights into training-free TAS, revealing the usefulness of evaluating Transformers based on the properties of their different blocks.
RESUMO
Depth information opens up new opportunities for video object segmentation (VOS) to be more accurate and robust in complex scenes. However, the RGBD VOS task is largely unexplored due to the expensive collection of RGBD data and time-consuming annotation of segmentation. In this work, we first introduce a new benchmark for RGBD VOS, named DepthVOS, which contains 350 videos (over 55k frames in total) annotated with masks and bounding boxes. We futher propose a novel, strong baseline model - Fused Color-Depth Network (FusedCDNet), which can be trained solely under the supervision of bounding boxes, while being used to generate masks with a bounding box guideline only in the first frame. Thereby, the model possesses three major advantages: a weakly-supervised training strategy to overcome the high-cost annotation, a cross-modal fusion module to handle complex scenes, and weakly-supervised inference to promote ease of use. Extensive experiments demonstrate that our proposed method performs on par with top fully-supervised algorithms. We will open-source our project on https://github.com/yjybuaa/depthvos/ to facilitate the development of RGBD VOS.
RESUMO
Graph Neural Networks have attracted increasing attention in recent years. However, existing GNN frameworks are deployed based upon simple graphs, which limits their applications in dealing with complex data correlation of multi-modal/multi-type data in practice. A few hypergraph-based methods have recently been proposed to address the problem of multi-modal/multi-type data correlation by directly concatenating the hypergraphs constructed from each single individual modality/type, which is difficult to learn an adaptive weight for each modality/type. In this paper, we extend the original conference version HGNN, and introduce a general high-order multi-modal/multi-type data correlation modeling framework called HGNN + to learn an optimal representation in a single hypergraph based framework. It is achieved by bridging multi-modal/multi-type data and hyperedge with hyperedge groups. Specifically, in our method, hyperedge groups are first constructed to represent latent high-order correlations in each specific modality/type with explicit or implicit graph structures. An adaptive hyperedge group fusion strategy is then used to effectively fuse the correlations from different modalities/types in a unified hypergraph. After that a new hypergraph convolution scheme performed in spatial domain is used to learn a general data representation for various tasks. We have evaluated this framework on several popular datasets and compared it with recent state-of-the-art methods. The comprehensive evaluations indicate that the proposed HGNN + framework can consistently outperform existing methods with a significant margin, especially when modeling implicit data correlations. We also release a toolbox called THU-DeepHypergraph for the proposed framework, which can be used for various of applications, such as data classification, retrieval and recommendation.
RESUMO
A resource-adaptive supernet adjusts its subnets for inference to fit the dynamically available resources. In this paper, we propose prioritized subnet sampling to train a resource-adaptive supernet, termed PSS-Net. We maintain multiple subnet pools, each of which stores the information of substantial subnets with similar resource consumption. Considering a resource constraint, subnets conditioned on this resource constraint are sampled from a pre-defined subnet structure space and high-quality ones will be inserted into the corresponding subnet pool. Then, the sampling will gradually be prone to sampling subnets from the subnet pools. Moreover, the one with a better performance metric is assigned with higher priority to train our PSS-Net, if sampling is from a subnet pool. At the end of training, our PSS-Net retains the best subnet in each pool to entitle a fast switch of high-quality subnets for inference when the available resources vary. Experiments on ImageNet using MobileNet-V1/V2 and ResNet-50 show that our PSS-Net can well outperform state-of-the-art resource-adaptive supernets. Our project is publicly available at https://github.com/chenbong/PSS-Net.
RESUMO
The mainstream approach for filter pruning is usually either to force a hard-coded importance estimation upon a computation-heavy pretrained model to select "important" filters, or to impose a hyperparameter-sensitive sparse constraint on the loss objective to regularize the network training. In this paper, we present a novel filter pruning method, dubbed dynamic-coded filter fusion (DCFF), to derive compact CNNs in a computation-economical and regularization-free manner for efficient image classification. Each filter in our DCFF is first given an inter-similarity distribution with a temperature parameter as a filter proxy, on top of which, a fresh Kullback-Leibler divergence based dynamic-coded criterion is proposed to evaluate the filter importance. In contrast to simply keeping high-score filters in other methods, we propose the concept of filter fusion, i.e., the weighted averages using the assigned proxies, as our preserved filters. We obtain a one-hot inter-similarity distribution as the temperature parameter approaches infinity. Thus, the relative importance of each filter can vary along with the training of the compact CNN, leading to dynamically changeable fused filters without both the dependency on the pretrained model and the introduction of sparse constraints. Extensive experiments on classification benchmarks demonstrate the superiority of our DCFF over the compared counterparts. For example, our DCFF derives a compact VGGNet-16 with only 72.77M FLOPs and 1.06M parameters while reaching top-1 accuracy of 93.47% on CIFAR-10. A compact ResNet-50 is obtained with 63.8% FLOPs and 58.6% parameter reductions, retaining 75.60% top-1 accuracy on ILSVRC-2012. Our code, narrower models and training logs are available at https://github.com/lmbxmu/DCFF.
RESUMO
Network pruning is an effective approach to reduce network complexity with acceptable performance compromise. Existing studies achieve the sparsity of neural networks via time-consuming weight training or complex searching on networks with expanded width, which greatly limits the applications of network pruning. In this paper, we show that high-performing and sparse sub-networks without the involvement of weight training, termed "lottery jackpots", exist in pre-trained models with unexpanded width. Our presented lottery jackpots are traceable through empirical and theoretical outcomes. For example, we obtain a lottery jackpot that has only 10% parameters and still reaches the performance of the original dense VGGNet-19 without any modifications on the pre-trained weights on CIFAR-10. Furthermore, we improve the efficiency for searching lottery jackpots from two perspectives. First, we observe that the sparse masks derived from many existing pruning criteria have a high overlap with the searched mask of our lottery jackpot, among which, the magnitude-based pruning results in the most similar mask with ours. In compliance with this insight, we initialize our sparse mask using the magnitude-based pruning, resulting in at least 3× cost reduction on the lottery jackpot searching while achieving comparable or even better performance. Second, we conduct an in-depth analysis of the searching process for lottery jackpots. Our theoretical result suggests that the decrease in training loss during weight searching can be disturbed by the dependency between weights in modern networks. To mitigate this, we propose a novel short restriction method to restrict change of masks that may have potential negative impacts on the training loss, which leads to a faster convergence and reduced oscillation for searching lottery jackpots. Consequently, our searched lottery jackpot removes 90% weights in ResNet-50, while it easily obtains more than 70% top-1 accuracy using only 5 searching epochs on ImageNet.
RESUMO
Existing online knowledge distillation approaches either adopt the student with the best performance or construct an ensemble model for better holistic performance. However, the former strategy ignores other students' information, while the latter increases the computational complexity during deployment. In this article, we propose a novel method for online knowledge distillation, termed feature fusion and self-distillation (FFSD), which comprises two key components: FFSD, toward solving the above problems in a unified framework. Different from previous works, where all students are treated equally, the proposed FFSD splits them into a leader student set and a common student set. Then, the feature fusion module converts the concatenation of feature maps from all common students into a fused feature map. The fused representation is used to assist the learning of the leader student. To enable the leader student to absorb more diverse information, we design an enhancement strategy to increase the diversity among students. Besides, a self-distillation module is adopted to convert the feature map of deeper layers into a shallower one. Then, the shallower layers are encouraged to mimic the transformed feature maps of the deeper layers, which helps the students to generalize better. After training, we simply adopt the leader student, which achieves superior performance, over the common students, without increasing the storage or inference cost. Extensive experiments on CIFAR-100 and ImageNet demonstrate the superiority of our FFSD over existing works. The code is available at https://github.com/SJLeo/FFSD.
RESUMO
Variation of scales or aspect ratios has been one of the main challenges for tracking. To overcome this challenge, most existing methods adopt either multi-scale search or anchor-based schemes, which use a predefined search space in a handcrafted way and therefore limit their performance in complicated scenes. To address this problem, recent anchor-free based trackers have been proposed without using prior scale or anchor information. However, an inconsistency problem between classification and regression degrades the tracking performance. To address the above issues, we propose a simple yet effective tracker (named Siamese Box Adaptive Network, SiamBAN) to learn a target-aware scale handling schema in a data-driven manner. Our basic idea is to predict the target boxes in a per-pixel fashion through a fully convolutional network, which is anchor-free. Specifically, SiamBAN divides the tracking problem into classification and regression tasks, which directly predict objectiveness and regress bounding boxes, respectively. A no-prior box design is proposed to avoid tuning hyper-parameters related to candidate boxes, which makes SiamBAN more flexible. SiamBAN further uses a target-aware branch to address the inconsistency problem. Experiments on benchmarks including VOT2018, VOT2019, OTB100, UAV123, LaSOT and TrackingNet show that SiamBAN achieves promising performance and runs at 35 FPS.
RESUMO
Channel pruning has been long studied to compress convolutional neural networks (CNNs), which significantly reduces the overall computation. Prior works implement channel pruning in an unexplainable manner, which tends to reduce the final classification errors while failing to consider the internal influence of each channel. In this article, we conduct channel pruning in a white box. Through deep visualization of feature maps activated by different channels, we observe that different channels have a varying contribution to different categories in image classification. Inspired by this, we choose to preserve channels contributing to most categories. Specifically, to model the contribution of each channel to differentiating categories, we develop a class-wise mask for each channel, implemented in a dynamic training manner with respect to the input image's category. On the basis of the learned class-wise mask, we perform a global voting mechanism to remove channels with less category discrimination. Lastly, a fine-tuning process is conducted to recover the performance of the pruned model. To our best knowledge, it is the first time that CNN interpretability theory is considered to guide channel pruning. Extensive experiments on representative image classification tasks demonstrate the superiority of our White-Box over many state-of-the-arts (SOTAs). For instance, on CIFAR-10, it reduces 65.23% floating point operations per seconds (FLOPs) with even 0.62% accuracy improvement for ResNet-110. On ILSVRC-2012, White-Box achieves a 45.6% FLOP reduction with only a small loss of 0.83% in the top-1 accuracy for ResNet-50. Code is available at https://github.com/zyxxmu/White-Box.
RESUMO
Few-shot class-incremental learning (FSCIL) is challenged by catastrophically forgetting old classes and over-fitting new classes. Revealed by our analyses, the problems are caused by feature distribution crumbling, which leads to class confusion when continuously embedding few samples to a fixed feature space. In this study, we propose a Dynamic Support Network (DSN), which refers to an adaptively updating network with compressive node expansion to "support" the feature space. In each training session, DSN tentatively expands network nodes to enlarge feature representation capacity for incremental classes. It then dynamically compresses the expanded network by node self-activation to pursue compact feature representation, which alleviates over-fitting. Simultaneously, DSN selectively recalls old class distributions during incremental learning to support feature distributions and avoid confusion between classes. DSN with compressive node expansion and class distribution recalling provides a systematic solution for the problems of catastrophic forgetting and overfitting. Experiments on CUB, CIFAR-100, and miniImage datasets show that DSN significantly improves upon the baseline approach, achieving new state-of-the-arts.